6 papers
Find, Fix, Reason: Context Repair for Video Reasoning
Haojian Huang, Chuanyu Qin, Yinchuan Li +1
Reinforcement learning has advanced video reasoning in large multi-modal models, yet dominant pipelines either rely on on-policy self-exploration, which plateaus at the model's kno…
DVD: Deterministic Video Depth Estimation with Generative Priors
Hongfei Zhang, Harold Haodong Chen, Chenfei Liao +12
Existing video depth estimation faces a fundamental trade-off: generative models suffer from stochastic geometric hallucinations and scale drift, while discriminative models demand…
Two-Steps Diffusion Policy for Robotic Manipulation via Genetic Denoising
Mateo Clemente, Leo Brunswic, Rui Heng Yang +5
Diffusion models, such as diffusion policy, have achieved state-of-the-art results in robotic manipulation by imitating expert demonstrations. While diffusion models were originall…
A Theory of Multi-Agent Generative Flow Networks
Leo Maxime Brunswic, Haozhi Wang, Shuang Luo +3
Generative flow networks utilize a flow-matching loss to learn a stochastic policy for generating objects from a sequence of actions, such that the probability of generating a patt…
Ergodic Generative Flows
Leo Maxime Brunswic, Mateo Clemente, Rui Heng Yang +3
Generative Flow Networks (GFNs) were initially introduced on directed acyclic graphs to sample from an unnormalized distribution density. Recent works have extended the theoretical…
RA-DP: Rapid Adaptive Diffusion Policy for Training-Free High-frequency Robotics Replanning
Xi Ye, Rui Heng Yang, Jun Jin +2
Diffusion models exhibit impressive scalability in robotic task learning, yet they struggle to adapt to novel, highly dynamic environments. This limitation primarily stems from the…